AI Product Engineer

This is a fully remote position, open to applicants in United Kingdom.

📋 Description

• Create agents that analyze incidents, uncover anomalies, address the question "why is production broken?", and utilize ClickStack as their foundation.

• Develop skills, not merely prompts. Establish a repository of reusable skills that encapsulates our team's approach to debugging, identifying root causes, formulating ClickHouse queries, and executing incident responses, ensuring agents select the appropriate playbook instead of starting from ground zero.

• Take full ownership of the agent stack from start to finish. This includes context engineering, tool design, evaluations, tracing, and cost management. You will be accountable for the agent's performance in production.

• Enhance ClickStack as an optimal platform for running AI workloads. Construct the MCP servers, SDKs, and integrations that empower customers' agents to interpret telemetry, take actions, and maintain their own observability.

• Collaborate openly. Engage with OSS contributors and customers, troubleshoot their issues alongside them, and integrate insights gained back into the product.

• Confront challenging aspects. Address issues related to latency, cost, context window limitations, evaluation coverage, and hallucinations with real telemetry.

⛳️ Requirements

• A minimum of 5 years of software engineering experience, including 1–2 years working with LLM-powered systems or agents in a production setting.

• Proficient backend development skills in TypeScript/Node.js and/or Python. Should be comfortable with both languages, even if one is the primary focus.

• Practical experience in building agents: multi-step tool usage, planning, memory management, and error recovery. You have successfully shipped them and navigated their potential failure modes.

• Proven experience in designing skills (Markdown-based workflow encodings, Anthropic-style or similar) with a clear understanding of when to use a skill, a tool, or both.

• Familiarity with MCP: building servers, designing tools, and considering authentication, scoping, and observability for agentic systems.

• Strong evaluation practices: familiarity with golden sets, LLM-as-judge methodologies, and regression detection.

• Proficiency in SQL — capable of writing ClickHouse queries directly.

• Comfortable working with Docker and Kubernetes.

• Actively engaged in open source projects and the developer community.

🏝️ Benefits

• Flexible work environment - ClickHouse is a globally distributed organization that supports remote work. We currently operate in over 20 countries.

• Healthcare - Employer contributions towards your healthcare expenses.

• Equity in the company - Each new team member who joins our company is granted stock options.

• Time off - Flexible time off policies in the US, with generous entitlements in other countries.

• A $500 Home office setup allowance for remote employees.

• Global Gatherings – We value the importance of in-person connections and provide opportunities for colleagues to engage at company-wide offsite events.